audit-ux-laws
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely documentation-driven. It provides a structured framework for an AI agent to analyze UI components using a set of local markdown reference files (
references/*.md). It does not request or require network access, file system write permissions, or the execution of external scripts. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to process user-provided UI code and layouts. While this creates a data ingestion surface for potentially untrusted content, the skill lacks the capabilities (such as network exfiltration or command execution) necessary to facilitate an exploit. The instructions explicitly direct the agent to use local reference files as the sole source of truth for its UX evaluations.
- [COMMAND_EXECUTION]: The README provides installation instructions using the
npx skillsCLI. These commands point to the author's own repository (yigitkonur/skills-by-yigitkonur) and are standard installation patterns for this ecosystem.
Audit Metadata